Explore Code

When you want to try a risky architecture change in a research codebase without polluting your main branch, this handles the isolated exploratory work. It transplants modules, swaps backbones, adds LoRA layers, or stitches together low-risk migration ideas while keeping rollback records in explore_outputs/. The key constraint is that the researcher must explicitly authorize the exploration and accept that results are candidates, not verified contributions. It won't touch your trusted baseline or handle conservative debugging. Honest take: the discipline of treating exploratory code as explicitly provisional is rare and worth enforcing, especially in research repos where "just trying something" can erase weeks of careful provenance.

skills.sh installs: 353K
GitHub stars: 486
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add lllllllama/rigorpilot-skills --skill explore-code --agent claude-code

Installs into .claude/skills of the current project.

Files

explore-code

Use this as the Rigor Improve implementation leaf skill. The installed slug remains explore-code for compatibility.

Use the shared operating principles in ../ai-research-reproduction/references/agent-operating-principles.md; this skill should guide bounded candidate code work without over-prescribing implementation details.

When to apply

When the researcher explicitly authorizes exploratory code changes on an isolated branch or worktree.
When the task is source-anchored module transplant, backbone adaptation, LoRA or adapter insertion, or low-risk module combination.
When summary-level recording is sufficient and the result is a candidate, not a trusted conclusion.

When not to apply

When the request is for trusted baseline work, conservative debugging, or normal training execution.
When the user did not explicitly authorize exploratory modifications.
When the task is a broad refactor or a from-scratch idea implementation.